Social network analysis of cell networks improves deep learning for prediction of molecular pathways and key mutations in colorectal cancer

CellOMaps: A compact representation for robust classification of lung adenocarcinoma growth patterns

Lung adenocarcinoma (LUAD) is a morphologically heterogeneous disease, characterized by five primary histological growth patterns. The classification of such patterns is crucial due to their direct relation to prognosis but the high subjectivity and observer variability pose a major challenge. Related studies in the literature focus on machine learning methods for growth pattern classification, often formulating the problem as a slide-level predominant pattern classification problem. We propose a generalizable machine learning pipeline capable of classifying lung tissue into one of the five patterns or as non-tumor. The proposed pipeline's strength lies in a novel compact Cell Organization Maps (cellOMaps) representation that captures the cellular spatial patterns from Hematoxylin and Eosin (H&E) whole slide images (WSIs). The proposed pipeline provides state-of-the-art performance on LUAD growth pattern classification when evaluated on both internal unseen slides and external datasets, comparing favorably with the current approaches. In addition, our preliminary results show that the model's outputs can be used to predict patients Tumor Mutational Burden (TMB) levels.

A visualization analysis of research on arterial compression hemostatic devices using VOSviewer and CiteSpace

Background

Cardiovascular and cerebrovascular diseases pose a significant health challenge in modern society, with the advancement of interventional therapy and vascular intervention technology playing crucial roles. In the context of post-interventional procedures, the application of suitable pressure at the puncture site is of utmost importance for achieving hemostasis. A variety of arterial compression devices are utilized in clinical settings to facilitate this critical step. A bibliometric analysis is used to assess the impact of research in a particular field. This study seeks to explore the research trends, key themes, and future directions of arterial compression hemostatic devices in international scholarly literature to inform future research endeavors.

Methods

English-language literature on arterial compression hemostatic devices was systematically retrieved from the Web of Science (WOS) and Scopus databases until December 31, 2024. In this study, we employed VOSviewer 1.6.18 and CiteSpace 6.2.r4 to systematically analyze a comprehensive set of parameters, which included authorship and institutional affiliations, geographical distribution by country, and thematic categorization through keywords.

Results

In total, 4,358 relevant publications were retrieved. This study's results section highlights a growing body of research on arterial compression hemostasis devices, with a significant increase in publications post-2000, reaching 107 in 2022. Department of Cardiology leads in institutional contributions, while 'Bernat, lvo' is the most prolific authors. Keyword analysis identifies "human," "article," "hemostasis," "female," and "male" as key terms, with 7 thematic clusters revealed by hierarchical clustering.

Conclusion

The results provide an overview of research on arterial compression hemostatic devices, which may help researchers better understand classical research, historical developments, and new discoveries, as well as providing ideas for future research.

Advances in Precision Medicine Approaches for Colorectal Cancer: From Molecular Profiling to Targeted Therapies

Precision medicine is transforming colorectal cancer treatment through the integration of advanced technologies and biomarkers, enhancing personalized and effective disease management. Identification of key driver mutations and molecular profiling have deepened our comprehension of the genetic alterations in colorectal cancer, facilitating targeted therapy and immunotherapy selection. Biomarkers such as microsatellite instability (MSI) and DNA mismatch repair deficiency (dMMR) guide treatment decisions, opening avenues for immunotherapy. Emerging technologies such as liquid biopsies, artificial intelligence, and machine learning promise to revolutionize early detection, monitoring, and treatment selection in precision medicine. Despite these advancements, ethical and regulatory challenges, including equitable access and data privacy, emphasize the importance of responsible implementation. The dynamic nature of colorectal cancer, with its tumor heterogeneity and clonal evolution, underscores the necessity for adaptive and personalized treatment strategies. The future of precision medicine in colorectal cancer lies in its potential to enhance patient care, clinical outcomes, and our understanding of this intricate disease, marked by ongoing evolution in the field. The current reviews focus on providing in-depth knowledge on the various and diverse approaches utilized for precision medicine against colorectal cancer, at both molecular and biochemical levels.